[PATCH v4 6/6] KVM: arm64: Use TLBI range-based intructions for unmap

[Raghavendra Rao Ananta]

The current implementation of the stage-2 unmap walker traverses
the given range and, as a part of break-before-make, performs
TLB invalidations with a DSB for every PTE. A multitude of this
combination could cause a performance bottleneck.

Hence, if the system supports FEAT_TLBIRANGE, defer the TLB
invalidations until the entire walk is finished, and then
use range-based instructions to invalidate the TLBs in one go.
Condition this upon S2FWB in order to avoid walking the page-table
again to perform the CMOs after issuing the TLBI.

Rename stage2_put_pte() to stage2_unmap_put_pte() as the function
now serves the stage-2 unmap walker specifically, rather than
acting generic.

Signed-off-by: Raghavendra Rao Ananta <rananta at google.com>
---
 arch/arm64/kvm/hyp/pgtable.c | 35 ++++++++++++++++++++++++++++++-----
 1 file changed, 30 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index b8f0dbd12f773..5832ee3418fb0 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -771,16 +771,34 @@ static void stage2_make_pte(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_t n
 	smp_store_release(ctx->ptep, new);
 }
 
-static void stage2_put_pte(const struct kvm_pgtable_visit_ctx *ctx, struct kvm_s2_mmu *mmu,
-			   struct kvm_pgtable_mm_ops *mm_ops)
+static bool stage2_unmap_defer_tlb_flush(struct kvm_pgtable *pgt)
 {
+	/*
+	 * If FEAT_TLBIRANGE is implemented, defer the individial PTE
+	 * TLB invalidations until the entire walk is finished, and
+	 * then use the range-based TLBI instructions to do the
+	 * invalidations. Condition this upon S2FWB in order to avoid
+	 * a page-table walk again to perform the CMOs after TLBI.
+	 */
+	return system_supports_tlb_range() && stage2_has_fwb(pgt);
+}
+
+static void stage2_unmap_put_pte(const struct kvm_pgtable_visit_ctx *ctx,
+				struct kvm_s2_mmu *mmu,
+				struct kvm_pgtable_mm_ops *mm_ops)
+{
+	struct kvm_pgtable *pgt = ctx->arg;
+
 	/*
 	 * Clear the existing PTE, and perform break-before-make with
 	 * TLB maintenance if it was valid.
 	 */
 	if (kvm_pte_valid(ctx->old)) {
 		kvm_clear_pte(ctx->ptep);
-		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, ctx->level);
+
+		if (!stage2_unmap_defer_tlb_flush(pgt))
+			kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu,
+					ctx->addr, ctx->level);
 	}
 
 	mm_ops->put_page(ctx->ptep);
@@ -1015,7 +1033,7 @@ static int stage2_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx,
 	 * block entry and rely on the remaining portions being faulted
 	 * back lazily.
 	 */
-	stage2_put_pte(ctx, mmu, mm_ops);
+	stage2_unmap_put_pte(ctx, mmu, mm_ops);
 
 	if (need_flush && mm_ops->dcache_clean_inval_poc)
 		mm_ops->dcache_clean_inval_poc(kvm_pte_follow(ctx->old, mm_ops),
@@ -1029,13 +1047,20 @@ static int stage2_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx,
 
 int kvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
 {
+	int ret;
 	struct kvm_pgtable_walker walker = {
 		.cb	= stage2_unmap_walker,
 		.arg	= pgt,
 		.flags	= KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST,
 	};
 
-	return kvm_pgtable_walk(pgt, addr, size, &walker);
+	ret = kvm_pgtable_walk(pgt, addr, size, &walker);
+	if (stage2_unmap_defer_tlb_flush(pgt))
+		/* Perform the deferred TLB invalidations */
+		kvm_call_hyp(__kvm_tlb_flush_vmid_range, pgt->mmu,
+				addr, addr + size);
+
+	return ret;
 }
 
 struct stage2_attr_data {
-- 
2.40.1.698.g37aff9b760-goog